CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-receptacle-searcher

This skill searches for a specific receptacle (e.g., garbage can, cabinet) by systematically exploring the environment, checking multiple locations until found. Trigger when the target receptacle is not initially visible, often after scanning nearby areas. It outputs the receptacle's location and may involve navigating through multiple waypoints.

57

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-receptacle-searcher/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clear, actionable procedural skill body with a well-sequenced workflow, but it underuses its own bundle: it duplicates environment/action details already in the reference file instead of linking to it, and never points to the search-pattern template asset.

Suggestions

Replace the inlined action set / observation-pattern detail with a one-level-deep link to references/environment_guide.md (e.g. 'See [environment_guide.md](references/environment_guide.md) for the action set and observation patterns') instead of duplicating that content.

Reference assets/search_pattern_template.json from the Core Procedure so the systematic-search step points to the template rather than restating the pattern.

Trim the 'Example from Trajectory' section to avoid restating the cabinet 1-20 sweep already covered in Core Procedure and Key Notes.

DimensionReasoningScore

Conciseness

The body is reasonably lean and avoids explaining concepts Claude already knows, but the 'Example from Trajectory' and 'Key Notes - Efficiency' sections restate steps already covered in Core Procedure (e.g. checking cabinets 1-20), so it could be tightened — matching the mostly-efficient anchor with some unnecessary repetition.

3 / 5

Actionability

Gives concrete, executable ALFWorld actions (`go to {recep}`), a worked example with specific receptacle identifiers, and explicit output guidance, with only minor gaps — matching the mostly-executable anchor rather than the fully copy-paste-ready level 5.

4 / 5

Workflow Clarity

The five-step Core Procedure is clearly sequenced (Identify → Initial Check → Systematic Search → Persistence → Output) with an explicit stop condition ('Continue until found') and an error-handling note for 'Nothing happened', leaving only minor validation gaps relative to the level-5 anchor with explicit feedback loops.

4 / 5

Progressive Disclosure

The body is well sectioned, but bundle files exist (references/environment_guide.md, assets/search_pattern_template.json) that are never referenced from SKILL.md, and action/observation details are inlined that already live in environment_guide.md — matching the anchor where references exist but are not clearly signaled and content that should be separate is inline.

3 / 5

Total

14

/

20

Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A solid, mostly concrete description that covers what the skill does and when to trigger it within the ALFWorld domain. Its main weakness is trigger-term phrasing that uses environment jargon over natural user verbs.

Suggestions

Add natural user-facing verbs such as 'find' or 'locate' (e.g. 'Use when you need to find or locate a receptacle that is not in view') so triggers match how a user would phrase the request.

Include synonyms and concrete name forms (e.g. 'garbagecan', 'cabinet N', 'drawer') alongside 'receptacle' to broaden keyword coverage.

Tighten the 'when' clause to a concrete trigger condition rather than the hedged 'often after scanning nearby areas'.

DimensionReasoningScore

Specificity

Names the domain (receptacle search) and several concrete actions — 'systematically exploring', 'checking multiple locations', 'outputs the receptacle's location', 'navigating through multiple waypoints' — with only minor coverage gaps, matching the anchor listing several specific actions.

4 / 5

Completeness

Explicitly answers both 'what' (searches/explores/outputs location) and 'when' ('Trigger when the target receptacle is not initially visible, often after scanning nearby areas'), but the 'when' clause is slightly conditional rather than a crisp concrete trigger, so it sits just below the level-5 anchor.

4 / 5

Trigger Term Quality

Includes relevant domain keywords ('receptacle', 'garbage can', 'cabinet', 'not initially visible', 'scanning nearby areas') but leans on ALFWorld jargon ('waypoints') and omits natural user verbs like 'find' or 'locate' and common synonyms, fitting the anchor with some relevant keywords but missing variations.

3 / 5

Distinctiveness Conflict Risk

Targets a narrow ALFWorld niche (receptacle search after failed initial scan) with distinct triggers; mostly distinct with only minor overlap risk against other ALFWorld navigation skills, matching the level-4 anchor rather than the fully-distinct level-5.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zjunlp/SkillNet
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.